AI-200: Azure AI Cloud Developer Associate Exam Prep

Clone or fork the Azure AI Cloud Developer repo from the public GitHub profile, then install VS Code, Bash (or PowerShell), Azure CLI, and Python to complete the hands-on labs.

Explore AI concepts like large language models, agents, and embeddings, and learn to deploy gen AI models with Microsoft Foundry platform for the AI 200 certification and retrieval augmented generation.

Explore core generative AI jargons, including tokens, system and user prompts, and the chat completions API, and compare multimodal and unimodal models for robust Azure AI development.

Deploy a Microsoft Foundry resource with a new resource group and project, then use the Foundry portal to access model catalog, endpoints, and AI services.

Explore how to call a large language model deployed in a Microsoft Foundry resource using the Foundry SDK, environment variables, and an OpenAI client to run chart completions.

Create your first Foundry agent, apply versioning and guardrails, attach tools like web search and code interpreter, and connect to enterprise knowledge via FoundryIQ with memory store.

Deploy a vector embedding engine in Microsoft Foundry, call it from the OpenAI SDK, and generate 1536-dimensional embeddings using text embedding ADA002.

Explore the world of containers and containerization, including Docker files, Docker images, and Docker containers, and learn how to replicate your development environment across machines and Azure cloud.

Install and run Docker Desktop to containerize your AI application for labs. Follow the installation guide and log in to build and push a container image to Azure resources.

Learn to build, test, and store container images in Azure Container Registry using ACR tasks, removing Docker runtime dependency and using az acr build to create and push images.

Deploy a container image from Azure Container Registry to an Azure web app on an App Service plan, with Linux hosting, managed identity, and port 5000.

Configure a container health check in your Azure App Service plan by pinging the /health endpoint, monitoring unhealthy instances, and automatically removing them from the load balancer.

Learn how Azure Key Vault securely stores secrets, API keys, connection strings, and certificates, and how a managed identity lets apps fetch these secrets via environment variables without hard coding.

Learn to integrate Azure Key Vault with an Azure Web App by storing secrets securely, configuring RBAC and managed identities, and referencing vault secrets in runtime environment variables.

Demonstrates enabling persistent storage in Azure app service for a Python app by storing chat histories in /home/chat_history and exposing /chat and /history endpoints, ensuring persistence across restarts.

Discover how to use the kudu console to inspect an azure web app's persistent storage, view environment variables and logs, and access persisted json files in the /home/chat_history folder.

Explore deployment slots in Azure web apps to host production, staging, and development environments, swap slots with near zero downtime, and integrate with ci/cd workflows and container registries.

Explore the basics of Kubernetes and Azure Kubernetes Service (AKS), including containerization, microservices, and orchestration rules, with emphasis on manifest files, scaling, and secure networking.

Deploy an Azure Kubernetes service (AKS) cluster in the Azure portal, configuring resource groups, node pools, networking, monitoring, security, and namespaces with system pods.

Connect to your Azure AKS cluster, using Azure CLI credentials, and inspect nodes, pods, and namespaces with kubectl. Install kubectl and verify the version to interact with kube-system namespaces.

Discover how Azure Container Registry integrates with AKS through a system-assigned managed identity that receives the ACR pull role, enabling AKS to pull and deploy container images.

Build a React chat app locally, containerize with Docker, push to Azure Container Registry, and prepare deployment to AKS using Azure OpenAI REST calls.

Create a yaml deployment manifest for a react.js app image from azure container registry, set replicas and port 80, then deploy to an aks cluster with kubectl.

Discover how Azure Kubernetes Service handles networking, including container-to-container, pod-to-pod, pod-to-service, and external-to-service communication, with Azure Load Balancer and services like clustered IP, node port, load balancer, and external name.

Learn how Azure Kubernetes Service uses config maps for endpoint and model name and secrets for API key to enable runtime injection and modularity.

Explore persistent volumes and persistent volume claims in AKS, using Azure file share to retain data across pod restarts, with YAML manifests and static and dynamic provisioning.

Understand Azure container apps environments, revisions, replicas, and jobs, including traffic splitting for revisions and scalable replicas for demand. Discover how consumption plan and workload profile influence compute and billing.

Learn to use environment variables and secrets to power a Python app in Azure container apps, including dockerization, Azure container registry deployment, and secret references to OpenAI endpoints.

Store the API key in Azure Key Vault and link it to an Azure container app using a user assigned managed identity. The app fetches key via a secret reference.

Azure Container Apps event-driven auto-scaling using HTTP scaler and blob storage rules, scaling replicas from one to ten during spikes and back, powered by KEDA.

Deploy an Azure Cosmos DB account for NoSQL, then create a database named food DB and a container named food container with the partition key category to optimize queries.

Boost query performance in Azure Cosmos DB by using range and composite indexes to avoid full container scans, optimize date range filters, and support multi-property, order-by queries.

Explore how to boost Azure Cosmos DB query performance by implementing range and composite indexes, optimizing filtering and sorting on rating, review count, and category.

Explore vector storage design in Azure Cosmos DB, including embedding field structure, vector embedding policy, dimensions, float32 data type, cosine similarity, and disk ANN indexing.

Integrate vector embeddings with a JSON data set in an Azure Cosmos DB container, using a vector policy and disk ANN index for retrieval augmented generation.

Learn to implement hybrid search in an Azure Cosmos DB container with vector embeddings, using full text and vector searches via reciprocal rank fusion, and generate embeddings with Azure OpenAI.

Build a retrieval augmented generation chatbot using Azure Cosmos DB vector embeddings, hybrid search, and GPD 4.1 via Azure OpenAI, with an augmented prompt system for accurate responses.

Azure managed postgres sql offers a platform as a service, a fully managed relational database with built-in backups, geo-replication, point-in-time restore, and schema-based organization for sales and production workloads.

Explore the ESG reporting case study for labs, modeling environmental emissions data in Azure managed Postgres SQL, covering scope one to three, indexing, queries, and rack chatbot with vector embeddings.

Learn to set up pgAdmin 4 to manage your PostgreSQL server in the Azure portal, connect by registering the server with host and port 5432, and access the default database.

Create and manage a PostgreSQL database in Azure by building an ESG schema with tables for companies, emissions, energy use, and sustainability reports, then insert and query sample data.

Use the ERD tool in pgAdmin4 to drag tables and visualize relationships, with companies table as parent and company_id as foreign key to sustainability reports, energy consumption, and emission records.

Demonstrate a code-first connection to Azure PostgreSQL with the PsychoPG SDK, configuring environment variables, creating a connection pool, and running selects with where, order by, and aggregations.

Learn how joins combine data from multiple tables using a common key, including inner, left, right, full, semi, anti, and cross joins, with practical examples in a star schema.

Explore inner joins, left inner joins, right inner joins, and full outer joins in PostgreSQL with sample scripts on a carbon targets dataset to retrieve company names and reduction targets.

Learn chunking strategies for a RAG pipeline, including fixed size with overlaps, semantic, and context enriched approaches, to preserve meaning and optimize vector embeddings and retrieval.

Enable the vector extension in Azure PostgreSQL to store vector embeddings and set up a RAG schema with ESG text data and ESG chunks tables, including a 1536-dimension vector column.

Implement semantic search in PostgreSQL by executing vector, keyword, and hybrid queries on embeddings to retrieve top relevant chunks with a reciprocal rank fusion score.

Deploy a hands-on lab to build a RAC chatbot with PostgreSQL, vector embeddings, and a hybrid search pipeline using Azure OpenAI to answer from retrieved context.

Explore Azure managed Redis as a fast in-memory cache and pubsub broker, with topics for subscribers, and data structures like strings, sets, hashes, plus shards and replicas for high availability.

Deploy an Azure managed Redis instance in the Azure portal with an in-memory data tier, 0.5 gb, 2 vcores, p0sku, public networking, and clustering for vector storage and vector search.

Execute a hands-on lab to connect to an Azure managed Redis instance by configuring hostname and password environment variables, and perform set and get, hash operations, and pipeline executions.

Compare Redis pubsub broadcast versus queue (streams) patterns to see how decoupled microservices use broadcast channels or competing consumers with persistence, retry, and backpressure.

Compare flat and hnsw vector indexing in Redis, noting accuracy and latency tradeoffs; outline embedding storage in a Redis hash with cosine similarity and ef runtime.

Upload a dataset to a redis instance with 1536-d vector embeddings, store them as redis hashes, and create an hnsw vector index to enable semantic search with the Ada002 model.

Run vector search similarity queries on Redis with embeddings and a KNN HNSW index; learn embedding generation, binary conversion, and cosine distance-based ranking.

Learn Azure Service Bus as a queue-based broker and pub-sub system using amqp, enabling competing consumers and topics with subscriptions for ai inference and rag workflows.

Compare Azure Service Bus and Redis messaging, noting Service Bus's durable storage and dead-letter queue versus Redis's fire-and-forget, ultra-low latency, to guide architecture choices.

Explore the Azure Service Bus message structure, including the request payload, message ID, content type, correlation ID, and application properties for filtering and for guiding large language model calls.

Explore Azure service bus message settlement types—complete, abandoned, dead-letter, and defer—and learn how each handles success, transient failures, and manual remediation in a peak lock queue system, including dead-letter queues.

Deploy an Azure service bus resource in the Azure portal, configure the resource group and namespace, and review standard pricing, topics and subscriptions, and access policies.

Process messages from an Azure Service Bus queue with a subscriber worker in peak lock mode, using Azure Open AI model deployment and dead-letter queue for errors.

Process dead-lettered messages from a primary queue using a dead-letter queue receiver in a service bus, parsing JSON payloads and invoking an Azure OpenAI model deployment to generate responses.

Set up an Azure Service Bus topic and two subscriptions with SQL filters to route messages to the Microsoft and ESG assistants, and configure topic creation, filters, and message routing.

Publish messages to an Azure Service Bus topic and route them to the Microsoft and ESG subscriptions using environment variables, a topic sender, and categorized service bus messages.

Learn to build and run subscription workers that process messages from Microsoft Learn and ESG subscriptions, routing queries to a tailored Azure OpenAI GPT-4.1 model with system prompts.

Implement the claim check pattern with Azure Service Bus to handle large payloads by storing images in Blob storage and sending image URLs in json for processing.